{
    "object_id": "https://biocomputeobject.org/GLY_000852/v-2.3.1",
    "etag": "27ebc541fa121a9f6dd9dff554b5be9a",
    "spec_version": "1.3.0",
    "provenance_domain": {
        "name": "Dicty Protein Names (NCBI RefSeq)",
        "version": "v-2.3.1",
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "created": "",
        "modified": "2024-01-09T05:00:11",
        "derived_from": [],
        "contributors": [
            {
                "name": "Jeet Vora",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "jeetvora@gwu.edu"
            },
            {
                "name": "Karina Martinez",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "karinamartinez@gwu.edu"
            },
            {
                "name": "Robel Kahsay",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "rykahsay@gwu.edu"
            },
            {
                "name": "Jingyue Wu",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "jingyue.wu@email.gwu.edu"
            }
        ],
        "review": []
    },
    "usability_domain": [
        "The Dicty Protein Names (NCBI RefSeq) dataset contains dicty [taxid:44689] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"
    ],
    "extension_domain": [
        {
            "dataset_extension": {
                "dataset_categories": [
                    {
                        "category_value": "Dictyostelium discoideum",
                        "category_name": "species"
                    },
                    {
                        "category_value": "Protein",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "Protein Names",
                        "category_name": "tag"
                    },
                    {
                        "category_value": "csv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    }
                ],
                "additional_license": {
                    "data_license": "https://creativecommons.org/licenses/by/4.0/",
                    "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html"
                }
            },
            "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"
        }
    ],
    "description_domain": {
        "keywords": [
            "protein names",
            "NCBI RefSeq"
        ],
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py",
                "version": "",
                "step_number": 1,
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": "The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"
            }
        ]
    },
    "execution_domain": {
        "external_data_endpoints": [],
        "environment_variables": {},
        "script_driver": "manual",
        "software_prerequisites": [
            {
                "version": "2.7.5",
                "name": "Python",
                "uri": {
                    "uri": "https://www.python.org/download/releases/2.7.5/"
                }
            }
        ],
        "script": [
            {
                "uri": {
                    "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py",
                    "filename": "make-protein-dataset.py"
                }
            }
        ]
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "io_domain": {
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_proteinnames_refseq.csv",
                    "filename": "dicty_protein_proteinnames_refseq.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_proteinnames_refseq.stat.csv",
                    "filename": "dicty_protein_proteinnames_refseq.stat.csv"
                }
            }
        ],
        "input_subdomain": [
            {
                "uri": {
                    "filename": "dicty_protein_xref_refseq.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_xref_refseq.csv"
                }
            }
        ]
    }
}